Average cost optimality of partially observed MDPs: contraction of nonlinear filters and existence of optimal solutions and approximations
From MaRDI portal
Publication:6640586
Recommendations
- Another look at partially observed optimal stochastic control: existence, ergodicity, and approximations without belief-reduction
- scientific article; zbMATH DE number 18469
- On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
- On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion
- On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
Cites work
- scientific article; zbMATH DE number 7625164 (Why is no real title available?)
- A further remark on dynamic programming for partially observed Markov processes
- Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
- Controlled Markov Processes with Arbitrary Numerical Criteria
- Convergence of Finite Memory Q Learning for POMDPs and Near Optimality of Learned Policies Under Filter Stability
- Dynamic Programming for Ergodic Control of Markov Chains under Partial Observations: A Correction
- Dynamic programming for ergodic control with partial observations.
- Exponential filter stability via Dobrushin's coefficient
- Finite approximations in discrete-time stochastic control. Quantized models and asymptotic optimality
- Incomplete information in Markovian decision models
- Long run control with degenerate observation
- Measure theory. Vol. I and II
- On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
- On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion
- Optimal Infinite-Horizon Undiscounted Control of Finite Probabilistic Systems
- Optimal Plans for Dynamic Programming Problems
- Partially observable total-cost Markov decision processes with weakly continuous transition probabilities
- Real Analysis and Probability
- Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
- Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes
- Robustness to Incorrect Priors in Partially Observed Stochastic Control
- Robustness to incorrect priors and controlled filter stability in partially observed stochastic control
- Robustness to incorrect system models in stochastic control
- Stability and uniform approximation of nonlinear filters using the Hilbert metric and application to particle filters
- Weak Feller property of non-linear filters
Cited in
(2)
This page was built for publication: Average cost optimality of partially observed MDPs: contraction of nonlinear filters and existence of optimal solutions and approximations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6640586)
